Starred repositories
The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.
A GUI for utilizing USBIP and Pipewire Source/Sink Streams on linux
Combustion engine simulation game that generates realistic audio.
Boxflat for Moza Racing. Control your Moza gear settings!
Lightweight & elastic kubernetes-native event streaming system
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
You like pytorch? You like micrograd? You love tinygrad! ❤️
TornadoVM: A practical and efficient heterogeneous programming framework for managed languages
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
A fast inference library for running LLMs locally on modern consumer-class GPUs
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Speech-to-text server framework with next-gen Kaldi
Visualizer for neural network, deep learning and machine learning models
A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web
Robust Speech Recognition via Large-Scale Weak Supervision
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Port of OpenAI's Whisper model in C/C++
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
Single Header Quite Fast QOI(Quite OK Image Format) Implementation written in C++20
A streaming QOI (Quite OK Image Format) decoder, designed for embedded systems with very little RAM.
An QOI codec that doesn't requires any other dependencies
GPU-Accelerated Lossless Data Compressors Survey